Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of ingredients in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pavia
    -0.91
     ControllerBase
    -0.85
    Diwedd
    -0.83
     '.')
    -0.82
    dafx
    -0.82
     nicio
    -0.81
     Popp
    -0.80
     Abbé
    -0.80
     picioare
    -0.80
    thâu
    -0.80
    POSITIVE LOGITS
     ingredients
    1.83
     ingredient
    1.55
     Ingredients
    1.54
     Ingredient
    1.49
    Ingredients
    1.45
    ingredients
    1.43
    Ingredient
    1.31
    ingredient
    1.26
     INGREDIENTS
    1.25
     ingredi
    1.25
    Act Density 0.101%

    No Known Activations